© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21023
    Prev
    Next
    INDEX
    Explanations

    degenerative diseases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iness
    -0.10
    /or
    -0.09
    ening
    -0.09
    inson
    -0.09
    side
    -0.09
    ings
    -0.08
    azes
    -0.08
    å¨ĺ
    -0.08
    atch
    -0.08
    ean
    -0.08
    POSITIVE LOGITS
    бой
    0.11
    oux
    0.10
    zo
    0.10
    oden
    0.10
     Ñģобой
    0.09
    ÂŃi
    0.09
    å¾Ĺ好
    0.09
    	TokenName
    0.09
    åħĪ导
    0.09
    ÙĬدÙĬ
    0.09
    Activations Density 0.015%

    No Known Activations